Upload 7 files
Browse files- README.md +51 -3
- config.json +20 -0
- fill-mask-result.png +0 -0
- gitattributes +28 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,51 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
thumbnail: https://github.com/jackaduma
|
4 |
+
tags:
|
5 |
+
- exbert
|
6 |
+
- security
|
7 |
+
- cybersecurity
|
8 |
+
- cyber security
|
9 |
+
- threat hunting
|
10 |
+
- threat intelligence
|
11 |
+
license: apache-2.0
|
12 |
+
datasets:
|
13 |
+
- APTnotes
|
14 |
+
- Stucco-Data
|
15 |
+
- CASIE
|
16 |
+
---
|
17 |
+
|
18 |
+
|
19 |
+
# SecBERT
|
20 |
+
|
21 |
+
This is the pretrained model presented in [SecBERT: A Pretrained Language Model for Cyber Security Text](https://github.com/jackaduma/SecBERT/), which is a BERT model trained on cyber security text.
|
22 |
+
|
23 |
+
The training corpus was papers taken from
|
24 |
+
* [APTnotes](https://github.com/kbandla/APTnotes)
|
25 |
+
* [Stucco-Data: Cyber security data sources](https://stucco.github.io/data/)
|
26 |
+
* [CASIE: Extracting Cybersecurity Event Information from Text](https://ebiquity.umbc.edu/_file_directory_/papers/943.pdf)
|
27 |
+
* [SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using Natural Language Processing (SecureNLP)](https://competitions.codalab.org/competitions/17262).
|
28 |
+
|
29 |
+
SecBERT has its own wordpiece vocabulary (secvocab) that's built to best match the training corpus.
|
30 |
+
|
31 |
+
We trained [SecBERT](https://huggingface.co/jackaduma/SecBERT) and [SecRoBERTa](https://huggingface.co/jackaduma/SecRoBERTa) versions.
|
32 |
+
|
33 |
+
Available models include:
|
34 |
+
* [`SecBERT`](https://huggingface.co/jackaduma/SecBERT)
|
35 |
+
* [`SecRoBERTa`](https://huggingface.co/jackaduma/SecRoBERTa)
|
36 |
+
|
37 |
+
---
|
38 |
+
## **Fill Mask**
|
39 |
+
|
40 |
+
We proposed to build language model which work on cyber security text, as result, it can improve downstream tasks (NER, Text Classification, Semantic Understand, Q&A) in Cyber Security Domain.
|
41 |
+
|
42 |
+
First, as below shows Fill-Mask pipeline in [Google Bert](), [AllenAI SciBert](https://github.com/allenai/scibert) and our [SecBERT](https://github.com/jackaduma/SecBERT) .
|
43 |
+
|
44 |
+
|
45 |
+
<!-- <img src="./fill-mask-result.png" width="150%" height="150%"> -->
|
46 |
+
|
47 |
+
![fill-mask-result](https://github.com/jackaduma/SecBERT/blob/main/fill-mask-result.png?raw=true)
|
48 |
+
|
49 |
+
---
|
50 |
+
|
51 |
+
The original repo can be found [here](https://github.com/jackaduma/SecBERT).
|
config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"gradient_checkpointing": false,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 514,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 6,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"type_vocab_size": 1,
|
19 |
+
"vocab_size": 52000
|
20 |
+
}
|
fill-mask-result.png
ADDED
gitattributes
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbc89dbadf58a8b0c3cbf574126c6ac71b9f8bbc1ad1bc0260636bf1051df06e
|
3 |
+
size 336396808
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08a1be6db1475e8cbcf7ffbc2f80a3b64b82cc62438260bf5cfdb1d385407a76
|
3 |
+
size 336411364
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|